In [ ]:
plt.figure(figsize=(10,10))
for i in range(12):
plt.subplot(3,4,i+1)
r=random.randint(0,1)
img = view_random_image(data_dir, class_names[r])
# pip install numpy;
# pip install pandas;
# pip install matplotlib
# pip install tensorflow
# pip install pydot
# pip install mlxtend
# pip install opencv-python
# pip install nbconvert
import os
import re
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import pandas as pd
%matplotlib inline
import warnings
warnings.filterwarnings("ignore")
import tensorflow as tf
from tensorflow.keras.callbacks import ModelCheckpoint
import glob
import random
from tensorflow.keras.preprocessing.image import ImageDataGenerator,load_img
from keras.utils.vis_utils import plot_model
from PIL import Image
from mlxtend.plotting import plot_confusion_matrix
from sklearn.metrics import confusion_matrix
import cv2 as cv
input_data="chest_Xray/"
train_directory= input_data + "train/"
val_directory= input_data + "val/"
test_directory= input_data + "test/"
data_dir = train_directory
class_names=os.listdir(train_directory)
print(class_names)
['NORMAL', 'PNEUMONIA']
# dir to generate files
FILES_GENERATED = 'files_generated/'
# name of model to save to png file
MODEL_PNG = 'cnn_model.png'
#checkpoint dir
CHECKPOINT_DIR = 'checkpoints/'
# name of best model to save
MODEL_SAVED = 'saved_model/model.h5'
# Default batch size
BATCH_SIZE = 32
def view_random_image(target_directory, target_class):
target_folder = target_directory + target_class
random_image = random.sample(os.listdir(target_folder), 1)
img = mpimg.imread(target_folder + "/" + random_image[0])
plt.imshow(img)
plt.title(target_class)
plt.axis("off");
return img
plt.figure(figsize=(10,10))
for i in range(12):
plt.subplot(3,4,i+1)
r=random.randint(0,1)
img = view_random_image(data_dir, class_names[r])
fig, ax = plt.subplots(2, 3, figsize=(15, 7))
ax = ax.ravel()
plt.tight_layout()
for i, _set in enumerate(['train', 'val', 'test']):
set_path = input_data + _set
ax[i].imshow(plt.imread(set_path+'/NORMAL/'+os.listdir(set_path+'/NORMAL')[0]), cmap='gray')
ax[i].set_title('Set: {}, Condition: Normal'.format(_set))
ax[i+3].imshow(plt.imread(set_path+'/PNEUMONIA/'+os.listdir(set_path+'/PNEUMONIA')[0]), cmap='gray')
ax[i+3].set_title('Set: {}, Condition: Pneumonia'.format(_set))
for _set in ['train', 'val', 'test']:
n_normal = len(os.listdir(input_data + _set + '/NORMAL'))
n_infect = len(os.listdir(input_data + _set + '/PNEUMONIA'))
print('Set: {}, Normal images: {}, pneumonia images: {}'.format(_set, n_normal, n_infect))
Set: train, Normal images: 1341, pneumonia images: 3875 Set: val, Normal images: 9, pneumonia images: 8 Set: test, Normal images: 234, pneumonia images: 390
It is used for getting the input of the original data and further, it makes the transformation of this data on a random basis and gives the output resultant containing only the data that is newly transformed. It does not add the data. Keras image data generator class is also used to carry out data augmentation where we aim to gain the overall increment in the generalization of the model. Operations such as rotations, translations, shearin, scale changes, and horizontal flips are carried out randomly in data augmentation using an image data generator.
Image_gen = ImageDataGenerator(
rescale = 1/255,
shear_range=10,
zoom_range=0.3,
horizontal_flip=True,
vertical_flip=True,
brightness_range=[0.5,2.0],
width_shift_range = 0.2,
rotation_range=20,
fill_mode = 'nearest'
)
val_Datagen = ImageDataGenerator(
rescale = 1/255
)
This method is useful when the images are sorted and placed in there respective class/label folders. This method will identify classes automatically from the folder name.
train = Image_gen.flow_from_directory(
train_directory,
batch_size=32,
class_mode='binary',
)
validation = Image_gen.flow_from_directory(
val_directory,
batch_size=2,
class_mode='binary',
)
test = val_Datagen.flow_from_directory(
test_directory,
batch_size=2,
class_mode='binary',
)
Found 5216 images belonging to 2 classes. Found 17 images belonging to 2 classes. Found 624 images belonging to 2 classes.
img, label = next(train)
In machine learning, early stopping is a form of regularization used to avoid overfitting when training a learner with an iterative method, such as gradient descent. Such methods update the learner so as to make it better fit the training data with each iteration. Up to a point, this improves the learner's performance on data outside of the training set. Past that point, however, improving the learner's fit to the training data comes at the expense of increased generalization error. Early stopping rules provide guidance as to how many iterations can be run before the learner begins to over-fit. Early stopping rules have been employed in many different machine learning methods, with varying amounts of theoretical foundation.
early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss',
patience=10)
Reduce learning rate when a metric has stopped improving.
Models often benefit from reducing the learning rate by a factor of 2-10 once learning stagnates. This callback monitors a quantity and if no improvement is seen for a 'patience' number of epochs, the learning rate is reduced.
lr = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss',
patience=8)
Reference
ResNet-50 is a convolutional neural network that is 50 layers deep. You can load a pretrained version of the network trained on more than a million images from the ImageNet database . The pretrained network can classify images into 1000 object categories, such as keyboard, mouse, pencil, and many animals.
def create_model():
resnet_model = tf.keras.applications.ResNet50V2(
weights='imagenet',
include_top = False,
input_shape = (224,224,3)
)
for layer in resnet_model.layers:
layer.trainable=False
x = resnet_model.output
x = tf.keras.layers.GlobalAveragePooling2D()(x)
x = tf.keras.layers.Dense(128,activation='relu')(x)
# output layer
predictions = tf.keras.layers.Dense(1,activation='sigmoid')(x)
res_model = tf.keras.Model(inputs=resnet_model.input, outputs=predictions)
# Compiling the model
res_model.compile(loss='binary_crossentropy', optimizer='adam',metrics=['accuracy'])
return res_model
res_model = create_model()
res_model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3 0 []
)]
conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 ['input_1[0][0]']
conv1_conv (Conv2D) (None, 112, 112, 64 9472 ['conv1_pad[0][0]']
)
pool1_pad (ZeroPadding2D) (None, 114, 114, 64 0 ['conv1_conv[0][0]']
)
pool1_pool (MaxPooling2D) (None, 56, 56, 64) 0 ['pool1_pad[0][0]']
conv2_block1_preact_bn (BatchN (None, 56, 56, 64) 256 ['pool1_pool[0][0]']
ormalization)
conv2_block1_preact_relu (Acti (None, 56, 56, 64) 0 ['conv2_block1_preact_bn[0][0]']
vation)
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) [(None, 224, 224, 3 0 []
)]
conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 ['input_1[0][0]']
conv1_conv (Conv2D) (None, 112, 112, 64 9472 ['conv1_pad[0][0]']
)
pool1_pad (ZeroPadding2D) (None, 114, 114, 64 0 ['conv1_conv[0][0]']
)
pool1_pool (MaxPooling2D) (None, 56, 56, 64) 0 ['pool1_pad[0][0]']
conv2_block1_preact_bn (BatchN (None, 56, 56, 64) 256 ['pool1_pool[0][0]']
ormalization)
conv2_block1_preact_relu (Acti (None, 56, 56, 64) 0 ['conv2_block1_preact_bn[0][0]']
vation)
conv2_block1_1_conv (Conv2D) (None, 56, 56, 64) 4096 ['conv2_block1_preact_relu[0][0]'
]
conv2_block1_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block1_1_conv[0][0]']
ization)
conv2_block1_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block1_1_bn[0][0]']
n)
conv2_block1_2_pad (ZeroPaddin (None, 58, 58, 64) 0 ['conv2_block1_1_relu[0][0]']
g2D)
conv2_block1_2_conv (Conv2D) (None, 56, 56, 64) 36864 ['conv2_block1_2_pad[0][0]']
conv2_block1_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block1_2_conv[0][0]']
ization)
conv2_block1_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block1_2_bn[0][0]']
n)
conv2_block1_0_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block1_preact_relu[0][0]'
]
conv2_block1_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block1_2_relu[0][0]']
conv2_block1_out (Add) (None, 56, 56, 256) 0 ['conv2_block1_0_conv[0][0]',
'conv2_block1_3_conv[0][0]']
conv2_block2_preact_bn (BatchN (None, 56, 56, 256) 1024 ['conv2_block1_out[0][0]']
ormalization)
conv2_block2_preact_relu (Acti (None, 56, 56, 256) 0 ['conv2_block2_preact_bn[0][0]']
vation)
conv2_block2_1_conv (Conv2D) (None, 56, 56, 64) 16384 ['conv2_block2_preact_relu[0][0]'
]
conv2_block2_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block2_1_conv[0][0]']
ization)
conv2_block2_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block2_1_bn[0][0]']
n)
conv2_block2_2_pad (ZeroPaddin (None, 58, 58, 64) 0 ['conv2_block2_1_relu[0][0]']
g2D)
conv2_block2_2_conv (Conv2D) (None, 56, 56, 64) 36864 ['conv2_block2_2_pad[0][0]']
conv2_block2_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block2_2_conv[0][0]']
ization)
conv2_block2_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block2_2_bn[0][0]']
n)
conv2_block2_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block2_2_relu[0][0]']
conv2_block2_out (Add) (None, 56, 56, 256) 0 ['conv2_block1_out[0][0]',
'conv2_block2_3_conv[0][0]']
conv2_block3_preact_bn (BatchN (None, 56, 56, 256) 1024 ['conv2_block2_out[0][0]']
ormalization)
conv2_block3_preact_relu (Acti (None, 56, 56, 256) 0 ['conv2_block3_preact_bn[0][0]']
vation)
conv2_block3_1_conv (Conv2D) (None, 56, 56, 64) 16384 ['conv2_block3_preact_relu[0][0]'
]
conv2_block3_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block3_1_conv[0][0]']
ization)
conv2_block3_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block3_1_bn[0][0]']
n)
conv2_block3_2_pad (ZeroPaddin (None, 58, 58, 64) 0 ['conv2_block3_1_relu[0][0]']
g2D)
conv2_block3_2_conv (Conv2D) (None, 28, 28, 64) 36864 ['conv2_block3_2_pad[0][0]']
conv2_block3_2_bn (BatchNormal (None, 28, 28, 64) 256 ['conv2_block3_2_conv[0][0]']
ization)
conv2_block3_2_relu (Activatio (None, 28, 28, 64) 0 ['conv2_block3_2_bn[0][0]']
n)
max_pooling2d (MaxPooling2D) (None, 28, 28, 256) 0 ['conv2_block2_out[0][0]']
conv2_block3_3_conv (Conv2D) (None, 28, 28, 256) 16640 ['conv2_block3_2_relu[0][0]']
conv2_block3_out (Add) (None, 28, 28, 256) 0 ['max_pooling2d[0][0]',
'conv2_block3_3_conv[0][0]']
conv3_block1_preact_bn (BatchN (None, 28, 28, 256) 1024 ['conv2_block3_out[0][0]']
ormalization)
conv3_block1_preact_relu (Acti (None, 28, 28, 256) 0 ['conv3_block1_preact_bn[0][0]']
vation)
conv3_block1_1_conv (Conv2D) (None, 28, 28, 128) 32768 ['conv3_block1_preact_relu[0][0]'
]
conv3_block1_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block1_1_conv[0][0]']
ization)
conv3_block1_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block1_1_bn[0][0]']
n)
conv3_block1_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block1_1_relu[0][0]']
g2D)
conv3_block1_2_conv (Conv2D) (None, 28, 28, 128) 147456 ['conv3_block1_2_pad[0][0]']
conv3_block1_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block1_2_conv[0][0]']
ization)
conv3_block1_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block1_2_bn[0][0]']
n)
conv3_block1_0_conv (Conv2D) (None, 28, 28, 512) 131584 ['conv3_block1_preact_relu[0][0]'
]
conv3_block1_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block1_2_relu[0][0]']
conv3_block1_out (Add) (None, 28, 28, 512) 0 ['conv3_block1_0_conv[0][0]',
'conv3_block1_3_conv[0][0]']
conv3_block2_preact_bn (BatchN (None, 28, 28, 512) 2048 ['conv3_block1_out[0][0]']
ormalization)
conv3_block2_preact_relu (Acti (None, 28, 28, 512) 0 ['conv3_block2_preact_bn[0][0]']
vation)
conv3_block2_1_conv (Conv2D) (None, 28, 28, 128) 65536 ['conv3_block2_preact_relu[0][0]'
]
conv3_block2_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block2_1_conv[0][0]']
ization)
conv3_block2_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block2_1_bn[0][0]']
n)
conv3_block2_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block2_1_relu[0][0]']
g2D)
conv3_block2_2_conv (Conv2D) (None, 28, 28, 128) 147456 ['conv3_block2_2_pad[0][0]']
conv3_block2_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block2_2_conv[0][0]']
ization)
conv3_block2_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block2_2_bn[0][0]']
n)
conv3_block2_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block2_2_relu[0][0]']
conv3_block2_out (Add) (None, 28, 28, 512) 0 ['conv3_block1_out[0][0]',
'conv3_block2_3_conv[0][0]']
conv3_block3_preact_bn (BatchN (None, 28, 28, 512) 2048 ['conv3_block2_out[0][0]']
ormalization)
conv3_block3_preact_relu (Acti (None, 28, 28, 512) 0 ['conv3_block3_preact_bn[0][0]']
vation)
conv3_block3_1_conv (Conv2D) (None, 28, 28, 128) 65536 ['conv3_block3_preact_relu[0][0]'
]
conv3_block3_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block3_1_conv[0][0]']
ization)
conv3_block3_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block3_1_bn[0][0]']
n)
conv3_block3_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block3_1_relu[0][0]']
g2D)
conv3_block3_2_conv (Conv2D) (None, 28, 28, 128) 147456 ['conv3_block3_2_pad[0][0]']
conv3_block3_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block3_2_conv[0][0]']
ization)
conv3_block3_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block3_2_bn[0][0]']
n)
conv3_block3_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block3_2_relu[0][0]']
conv3_block3_out (Add) (None, 28, 28, 512) 0 ['conv3_block2_out[0][0]',
'conv3_block3_3_conv[0][0]']
conv3_block4_preact_bn (BatchN (None, 28, 28, 512) 2048 ['conv3_block3_out[0][0]']
ormalization)
conv3_block4_preact_relu (Acti (None, 28, 28, 512) 0 ['conv3_block4_preact_bn[0][0]']
vation)
conv3_block4_1_conv (Conv2D) (None, 28, 28, 128) 65536 ['conv3_block4_preact_relu[0][0]'
]
conv3_block4_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block4_1_conv[0][0]']
ization)
conv3_block4_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block4_1_bn[0][0]']
n)
conv3_block4_2_pad (ZeroPaddin (None, 30, 30, 128) 0 ['conv3_block4_1_relu[0][0]']
g2D)
conv3_block4_2_conv (Conv2D) (None, 14, 14, 128) 147456 ['conv3_block4_2_pad[0][0]']
conv3_block4_2_bn (BatchNormal (None, 14, 14, 128) 512 ['conv3_block4_2_conv[0][0]']
ization)
conv3_block4_2_relu (Activatio (None, 14, 14, 128) 0 ['conv3_block4_2_bn[0][0]']
n)
max_pooling2d_1 (MaxPooling2D) (None, 14, 14, 512) 0 ['conv3_block3_out[0][0]']
conv3_block4_3_conv (Conv2D) (None, 14, 14, 512) 66048 ['conv3_block4_2_relu[0][0]']
conv3_block4_out (Add) (None, 14, 14, 512) 0 ['max_pooling2d_1[0][0]',
'conv3_block4_3_conv[0][0]']
conv4_block1_preact_bn (BatchN (None, 14, 14, 512) 2048 ['conv3_block4_out[0][0]']
ormalization)
conv4_block1_preact_relu (Acti (None, 14, 14, 512) 0 ['conv4_block1_preact_bn[0][0]']
vation)
conv4_block1_1_conv (Conv2D) (None, 14, 14, 256) 131072 ['conv4_block1_preact_relu[0][0]'
]
conv4_block1_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block1_1_conv[0][0]']
ization)
conv4_block1_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block1_1_bn[0][0]']
n)
conv4_block1_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block1_1_relu[0][0]']
g2D)
conv4_block1_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block1_2_pad[0][0]']
conv4_block1_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block1_2_conv[0][0]']
ization)
conv4_block1_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block1_2_bn[0][0]']
n)
conv4_block1_0_conv (Conv2D) (None, 14, 14, 1024 525312 ['conv4_block1_preact_relu[0][0]'
) ]
conv4_block1_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block1_2_relu[0][0]']
)
conv4_block1_out (Add) (None, 14, 14, 1024 0 ['conv4_block1_0_conv[0][0]',
) 'conv4_block1_3_conv[0][0]']
conv4_block2_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block1_out[0][0]']
ormalization) )
conv4_block2_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block2_preact_bn[0][0]']
vation) )
conv4_block2_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block2_preact_relu[0][0]'
]
conv4_block2_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block2_1_conv[0][0]']
ization)
conv4_block2_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block2_1_bn[0][0]']
n)
conv4_block2_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block2_1_relu[0][0]']
g2D)
conv4_block2_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block2_2_pad[0][0]']
conv4_block2_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block2_2_conv[0][0]']
ization)
conv4_block2_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block2_2_bn[0][0]']
n)
conv4_block2_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block2_2_relu[0][0]']
)
conv4_block2_out (Add) (None, 14, 14, 1024 0 ['conv4_block1_out[0][0]',
) 'conv4_block2_3_conv[0][0]']
conv4_block3_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block2_out[0][0]']
ormalization) )
conv4_block3_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block3_preact_bn[0][0]']
vation) )
conv4_block3_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block3_preact_relu[0][0]'
]
conv4_block3_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block3_1_conv[0][0]']
ization)
conv4_block3_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block3_1_bn[0][0]']
n)
conv4_block3_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block3_1_relu[0][0]']
g2D)
conv4_block3_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block3_2_pad[0][0]']
conv4_block3_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block3_2_conv[0][0]']
ization)
conv4_block3_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block3_2_bn[0][0]']
n)
conv4_block3_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block3_2_relu[0][0]']
)
conv4_block3_out (Add) (None, 14, 14, 1024 0 ['conv4_block2_out[0][0]',
) 'conv4_block3_3_conv[0][0]']
conv4_block4_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block3_out[0][0]']
ormalization) )
conv4_block4_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block4_preact_bn[0][0]']
vation) )
conv4_block4_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block4_preact_relu[0][0]'
]
conv4_block4_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block4_1_conv[0][0]']
ization)
conv4_block4_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block4_1_bn[0][0]']
n)
conv4_block4_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block4_1_relu[0][0]']
g2D)
conv4_block4_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block4_2_pad[0][0]']
conv4_block4_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block4_2_conv[0][0]']
ization)
conv4_block4_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block4_2_bn[0][0]']
n)
conv4_block4_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block4_2_relu[0][0]']
)
conv4_block4_out (Add) (None, 14, 14, 1024 0 ['conv4_block3_out[0][0]',
) 'conv4_block4_3_conv[0][0]']
conv4_block5_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block4_out[0][0]']
ormalization) )
conv4_block5_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block5_preact_bn[0][0]']
vation) )
conv4_block5_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block5_preact_relu[0][0]'
]
conv4_block5_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block5_1_conv[0][0]']
ization)
conv4_block5_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block5_1_bn[0][0]']
n)
conv4_block5_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block5_1_relu[0][0]']
g2D)
conv4_block5_2_conv (Conv2D) (None, 14, 14, 256) 589824 ['conv4_block5_2_pad[0][0]']
conv4_block5_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block5_2_conv[0][0]']
ization)
conv4_block5_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block5_2_bn[0][0]']
n)
conv4_block5_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block5_2_relu[0][0]']
)
conv4_block5_out (Add) (None, 14, 14, 1024 0 ['conv4_block4_out[0][0]',
) 'conv4_block5_3_conv[0][0]']
conv4_block6_preact_bn (BatchN (None, 14, 14, 1024 4096 ['conv4_block5_out[0][0]']
ormalization) )
conv4_block6_preact_relu (Acti (None, 14, 14, 1024 0 ['conv4_block6_preact_bn[0][0]']
vation) )
conv4_block6_1_conv (Conv2D) (None, 14, 14, 256) 262144 ['conv4_block6_preact_relu[0][0]'
]
conv4_block6_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block6_1_conv[0][0]']
ization)
conv4_block6_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block6_1_bn[0][0]']
n)
conv4_block6_2_pad (ZeroPaddin (None, 16, 16, 256) 0 ['conv4_block6_1_relu[0][0]']
g2D)
conv4_block6_2_conv (Conv2D) (None, 7, 7, 256) 589824 ['conv4_block6_2_pad[0][0]']
conv4_block6_2_bn (BatchNormal (None, 7, 7, 256) 1024 ['conv4_block6_2_conv[0][0]']
ization)
conv4_block6_2_relu (Activatio (None, 7, 7, 256) 0 ['conv4_block6_2_bn[0][0]']
n)
max_pooling2d_2 (MaxPooling2D) (None, 7, 7, 1024) 0 ['conv4_block5_out[0][0]']
conv4_block6_3_conv (Conv2D) (None, 7, 7, 1024) 263168 ['conv4_block6_2_relu[0][0]']
conv4_block6_out (Add) (None, 7, 7, 1024) 0 ['max_pooling2d_2[0][0]',
'conv4_block6_3_conv[0][0]']
conv5_block1_preact_bn (BatchN (None, 7, 7, 1024) 4096 ['conv4_block6_out[0][0]']
ormalization)
conv5_block1_preact_relu (Acti (None, 7, 7, 1024) 0 ['conv5_block1_preact_bn[0][0]']
vation)
conv5_block1_1_conv (Conv2D) (None, 7, 7, 512) 524288 ['conv5_block1_preact_relu[0][0]'
]
conv5_block1_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block1_1_conv[0][0]']
ization)
conv5_block1_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block1_1_bn[0][0]']
n)
conv5_block1_2_pad (ZeroPaddin (None, 9, 9, 512) 0 ['conv5_block1_1_relu[0][0]']
g2D)
conv5_block1_2_conv (Conv2D) (None, 7, 7, 512) 2359296 ['conv5_block1_2_pad[0][0]']
conv5_block1_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block1_2_conv[0][0]']
ization)
conv5_block1_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block1_2_bn[0][0]']
n)
conv5_block1_0_conv (Conv2D) (None, 7, 7, 2048) 2099200 ['conv5_block1_preact_relu[0][0]'
]
conv5_block1_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block1_2_relu[0][0]']
conv5_block1_out (Add) (None, 7, 7, 2048) 0 ['conv5_block1_0_conv[0][0]',
'conv5_block1_3_conv[0][0]']
conv5_block2_preact_bn (BatchN (None, 7, 7, 2048) 8192 ['conv5_block1_out[0][0]']
ormalization)
conv5_block2_preact_relu (Acti (None, 7, 7, 2048) 0 ['conv5_block2_preact_bn[0][0]']
vation)
conv5_block2_1_conv (Conv2D) (None, 7, 7, 512) 1048576 ['conv5_block2_preact_relu[0][0]'
]
conv5_block2_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block2_1_conv[0][0]']
ization)
conv5_block2_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block2_1_bn[0][0]']
n)
conv5_block2_2_pad (ZeroPaddin (None, 9, 9, 512) 0 ['conv5_block2_1_relu[0][0]']
g2D)
conv5_block2_2_conv (Conv2D) (None, 7, 7, 512) 2359296 ['conv5_block2_2_pad[0][0]']
conv5_block2_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block2_2_conv[0][0]']
ization)
conv5_block2_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block2_2_bn[0][0]']
n)
conv5_block2_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block2_2_relu[0][0]']
conv5_block2_out (Add) (None, 7, 7, 2048) 0 ['conv5_block1_out[0][0]',
'conv5_block2_3_conv[0][0]']
conv5_block3_preact_bn (BatchN (None, 7, 7, 2048) 8192 ['conv5_block2_out[0][0]']
ormalization)
conv5_block3_preact_relu (Acti (None, 7, 7, 2048) 0 ['conv5_block3_preact_bn[0][0]']
vation)
conv5_block3_1_conv (Conv2D) (None, 7, 7, 512) 1048576 ['conv5_block3_preact_relu[0][0]'
]
conv5_block3_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block3_1_conv[0][0]']
ization)
conv5_block3_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block3_1_bn[0][0]']
n)
conv5_block3_2_pad (ZeroPaddin (None, 9, 9, 512) 0 ['conv5_block3_1_relu[0][0]']
g2D)
conv5_block3_2_conv (Conv2D) (None, 7, 7, 512) 2359296 ['conv5_block3_2_pad[0][0]']
conv5_block3_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block3_2_conv[0][0]']
ization)
conv5_block3_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block3_2_bn[0][0]']
n)
conv5_block3_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block3_2_relu[0][0]']
conv5_block3_out (Add) (None, 7, 7, 2048) 0 ['conv5_block2_out[0][0]',
'conv5_block3_3_conv[0][0]']
post_bn (BatchNormalization) (None, 7, 7, 2048) 8192 ['conv5_block3_out[0][0]']
post_relu (Activation) (None, 7, 7, 2048) 0 ['post_bn[0][0]']
global_average_pooling2d (Glob (None, 2048) 0 ['post_relu[0][0]']
alAveragePooling2D)
dense (Dense) (None, 128) 262272 ['global_average_pooling2d[0][0]'
]
dense_1 (Dense) (None, 1) 129 ['dense[0][0]']
==================================================================================================
Total params: 23,827,201
Trainable params: 262,401
Non-trainable params: 23,564,800
__________________________________________________________________________________________________
plot_model(res_model, to_file=FILES_GENERATED + MODEL_PNG, show_shapes=True, show_layer_names=True)
display(Image.open(FILES_GENERATED + MODEL_PNG))
checkpoint_path = CHECKPOINT_DIR + "cp-{epoch:04d}.ckpt"
# Create a callback that saves the model's weights every 5 epochs
cp_callback = tf.keras.callbacks.ModelCheckpoint(
filepath=checkpoint_path,
verbose=1,
save_weights_only=True,
save_freq=5*BATCH_SIZE)
# Create a callback allowing to save the best performing model
checkpoint = ModelCheckpoint(MODEL_SAVED, monitor='val_loss', verbose=1, save_best_only=True, mode='auto')
history = res_model.fit(train,epochs=30,
validation_data=validation,
steps_per_epoch=100,
callbacks=[early_stopping,lr, checkpoint],
batch_size=32)
Epoch 1/30 100/100 [==============================] - ETA: 0s - loss: 0.3233 - accuracy: 0.8537 Epoch 1: val_loss improved from inf to 0.80012, saving model to saved_model\model.h5 100/100 [==============================] - 131s 1s/step - loss: 0.3233 - accuracy: 0.8537 - val_loss: 0.8001 - val_accuracy: 0.7059 - lr: 0.0010 Epoch 2/30 100/100 [==============================] - ETA: 0s - loss: 0.2152 - accuracy: 0.9137 Epoch 2: val_loss did not improve from 0.80012 100/100 [==============================] - 125s 1s/step - loss: 0.2152 - accuracy: 0.9137 - val_loss: 0.9429 - val_accuracy: 0.6471 - lr: 0.0010 Epoch 3/30 100/100 [==============================] - ETA: 0s - loss: 0.1885 - accuracy: 0.9256 Epoch 3: val_loss improved from 0.80012 to 0.50200, saving model to saved_model\model.h5 100/100 [==============================] - 125s 1s/step - loss: 0.1885 - accuracy: 0.9256 - val_loss: 0.5020 - val_accuracy: 0.8235 - lr: 0.0010 Epoch 4/30 100/100 [==============================] - ETA: 0s - loss: 0.1825 - accuracy: 0.9266 Epoch 4: val_loss did not improve from 0.50200 100/100 [==============================] - 128s 1s/step - loss: 0.1825 - accuracy: 0.9266 - val_loss: 0.7413 - val_accuracy: 0.7059 - lr: 0.0010 Epoch 5/30 100/100 [==============================] - ETA: 0s - loss: 0.1922 - accuracy: 0.9244 Epoch 5: val_loss did not improve from 0.50200 100/100 [==============================] - 127s 1s/step - loss: 0.1922 - accuracy: 0.9244 - val_loss: 1.0950 - val_accuracy: 0.5882 - lr: 0.0010 Epoch 6/30 100/100 [==============================] - ETA: 0s - loss: 0.1846 - accuracy: 0.9303 Epoch 6: val_loss improved from 0.50200 to 0.26534, saving model to saved_model\model.h5 100/100 [==============================] - 129s 1s/step - loss: 0.1846 - accuracy: 0.9303 - val_loss: 0.2653 - val_accuracy: 0.8235 - lr: 0.0010 Epoch 7/30 100/100 [==============================] - ETA: 0s - loss: 0.1519 - accuracy: 0.9356 Epoch 7: val_loss did not improve from 0.26534 100/100 [==============================] - 129s 1s/step - loss: 0.1519 - accuracy: 0.9356 - val_loss: 0.2674 - val_accuracy: 0.8824 - lr: 0.0010 Epoch 8/30 100/100 [==============================] - ETA: 0s - loss: 0.1720 - accuracy: 0.9303 Epoch 8: val_loss did not improve from 0.26534 100/100 [==============================] - 128s 1s/step - loss: 0.1720 - accuracy: 0.9303 - val_loss: 0.4274 - val_accuracy: 0.7647 - lr: 0.0010 Epoch 9/30 100/100 [==============================] - ETA: 0s - loss: 0.1589 - accuracy: 0.9372 Epoch 9: val_loss did not improve from 0.26534 100/100 [==============================] - 117s 1s/step - loss: 0.1589 - accuracy: 0.9372 - val_loss: 0.3695 - val_accuracy: 0.8235 - lr: 0.0010 Epoch 10/30 100/100 [==============================] - ETA: 0s - loss: 0.1546 - accuracy: 0.9356 Epoch 10: val_loss did not improve from 0.26534 100/100 [==============================] - 111s 1s/step - loss: 0.1546 - accuracy: 0.9356 - val_loss: 0.2721 - val_accuracy: 0.8235 - lr: 0.0010 Epoch 11/30 100/100 [==============================] - ETA: 0s - loss: 0.1603 - accuracy: 0.9375 Epoch 11: val_loss improved from 0.26534 to 0.10197, saving model to saved_model\model.h5 100/100 [==============================] - 116s 1s/step - loss: 0.1603 - accuracy: 0.9375 - val_loss: 0.1020 - val_accuracy: 1.0000 - lr: 0.0010 Epoch 12/30 100/100 [==============================] - ETA: 0s - loss: 0.1618 - accuracy: 0.9369 Epoch 12: val_loss did not improve from 0.10197 100/100 [==============================] - 116s 1s/step - loss: 0.1618 - accuracy: 0.9369 - val_loss: 0.4099 - val_accuracy: 0.8824 - lr: 0.0010 Epoch 13/30 100/100 [==============================] - ETA: 0s - loss: 0.1556 - accuracy: 0.9388 Epoch 13: val_loss did not improve from 0.10197 100/100 [==============================] - 116s 1s/step - loss: 0.1556 - accuracy: 0.9388 - val_loss: 0.2962 - val_accuracy: 0.8824 - lr: 0.0010 Epoch 14/30 100/100 [==============================] - ETA: 0s - loss: 0.1514 - accuracy: 0.9372 Epoch 14: val_loss did not improve from 0.10197 100/100 [==============================] - 114s 1s/step - loss: 0.1514 - accuracy: 0.9372 - val_loss: 0.2176 - val_accuracy: 0.9412 - lr: 0.0010 Epoch 15/30 100/100 [==============================] - ETA: 0s - loss: 0.1529 - accuracy: 0.9347 Epoch 15: val_loss did not improve from 0.10197 100/100 [==============================] - 114s 1s/step - loss: 0.1529 - accuracy: 0.9347 - val_loss: 0.3605 - val_accuracy: 0.7647 - lr: 0.0010 Epoch 16/30 100/100 [==============================] - ETA: 0s - loss: 0.1502 - accuracy: 0.9406 Epoch 16: val_loss did not improve from 0.10197 100/100 [==============================] - 115s 1s/step - loss: 0.1502 - accuracy: 0.9406 - val_loss: 0.2702 - val_accuracy: 0.9412 - lr: 0.0010 Epoch 17/30 100/100 [==============================] - ETA: 0s - loss: 0.1713 - accuracy: 0.9278 Epoch 17: val_loss did not improve from 0.10197 100/100 [==============================] - 114s 1s/step - loss: 0.1713 - accuracy: 0.9278 - val_loss: 0.6252 - val_accuracy: 0.8235 - lr: 0.0010 Epoch 18/30 100/100 [==============================] - ETA: 0s - loss: 0.1363 - accuracy: 0.9456 Epoch 18: val_loss did not improve from 0.10197 100/100 [==============================] - 114s 1s/step - loss: 0.1363 - accuracy: 0.9456 - val_loss: 0.3363 - val_accuracy: 0.8824 - lr: 0.0010 Epoch 19/30 100/100 [==============================] - ETA: 0s - loss: 0.1344 - accuracy: 0.9447 Epoch 19: val_loss did not improve from 0.10197 100/100 [==============================] - 117s 1s/step - loss: 0.1344 - accuracy: 0.9447 - val_loss: 0.3291 - val_accuracy: 0.9412 - lr: 0.0010 Epoch 20/30 100/100 [==============================] - ETA: 0s - loss: 0.1294 - accuracy: 0.9484 Epoch 20: val_loss did not improve from 0.10197 100/100 [==============================] - 120s 1s/step - loss: 0.1294 - accuracy: 0.9484 - val_loss: 0.9169 - val_accuracy: 0.7059 - lr: 1.0000e-04 Epoch 21/30 100/100 [==============================] - ETA: 0s - loss: 0.1311 - accuracy: 0.9491 Epoch 21: val_loss did not improve from 0.10197 100/100 [==============================] - 120s 1s/step - loss: 0.1311 - accuracy: 0.9491 - val_loss: 0.3360 - val_accuracy: 0.7647 - lr: 1.0000e-04
#Plot the training artifacts
fig , ax = plt.subplots(1, 2)
fig.set_size_inches(20, 10)
train_acc = history.history['accuracy']
train_loss = history.history['loss']
val_acc = history.history['val_accuracy']
val_loss = history.history['val_loss']
epochs = range(1, len(train_acc) + 1)
ax[0].plot(epochs, train_acc , 'go-' , label = 'Training Accuracy')
ax[0].plot(epochs , val_acc , 'yo-' , label = 'Validation Accuracy')
ax[0].set_title('Model Train & Validation Accuracy')
ax[0].legend()
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('Accuracy')
ax[1].plot(epochs, train_loss , 'go-' , label = 'Training Loss')
ax[1].plot(epochs, val_loss , 'yo-' , label = 'Validation Loss')
ax[1].set_title('Model Train & Validation Loss')
ax[1].legend()
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Loss')
Text(0, 0.5, 'Loss')
# Evaluating the model on train and test
score = res_model.evaluate(train)
print("Train Loss: ", score[0])
print("Train Accuracy: ", score[1])
score = res_model.evaluate(test)
print("\nTest loss: ", score[0])
print("Test Accuracy: ", score[1])
163/163 [==============================] - 186s 1s/step - loss: 0.1238 - accuracy: 0.9519 Train Loss: 0.12377023696899414 Train Accuracy: 0.9518788456916809 312/312 [==============================] - 26s 83ms/step - loss: 0.2332 - accuracy: 0.9167 Test loss: 0.2332271933555603 Test Accuracy: 0.9166666865348816